Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Writing code is cheap now

simonwillison.net

Post reply on HN
Print view View original

481–490 of 522 posts

Re: Writing code is cheap now

#481

Post by hansmayer »

Quothling wrote: post #460
hansmayer wrote: post #456

Earlier quoted context omitted.

Code reviews are pseudo-science now? Computer unfriendly code? What are you talking about? Do you understand that this babble makes zero sense ? Are you one of those product managers who recently learned to vibe-code? If so, make sure your latest Replit project does not delete your production database..

Splitting your code up into multiple functions across multiple files is computer unfriendly code. It'll cause L1, L2 and L3 cache misses. Yet it's heailed as very human friendly and maintainable by Uncle Bob and his disciples. As far as code reviews go, do you have any form of evidence that it's not a pseudo science? If I look at our industry today, it's not like it's in better shape compared to where it was decades…

> Splitting your code up into multiple functions across multiple files is computer unfriendly code. It'll cause L1, L2 and L3 cache misses

I think you have no idea what you're talking about and trying to sound technical based on some concepts you misheard somewhere.

A lot of non-tech people got into "tech" in the last years not because they were passionate about technology but because they heard they could make more money there. This was possible due to VCs throwing around money at various software companies. As a result we get statements like yours. There is one thing that I am hopeful for with the AI bubble - which is the VCs panicking out because they think "everyone will vibecode an SaaS" - and pulling out of software companies investments, causing the folks like you to go back to whatever you were doing before and leaving software to people who actually know it and do it out of genuine interest and not primarily for the money.

Re: Writing code is cheap now

#482

Post by tonyedgecombe »

Itoldmyselfso wrote: post #329
Retr0id wrote: post #312

Earlier quoted context omitted.

What are some examples of when buggy code can be tolerated?

Points at the public sector

Any large enterprise. The software organisations write for themselves is pretty dire in most cases even without AI.

Re: Writing code is cheap now

#483

Post by skinner_ »

jimbokun wrote: post #454
manuelabeledo wrote: post #322

Earlier quoted context omitted.

Unless the specification is also free of bugs and side effects, there is no guarantee that a rewrite would have fewer bugs. Plenty of rewrites out there prove that point.

Seems relevant again: https://www.joelonsoftware.com/2000/04/06/things-you-should-...

I think the nuanced take on Joel's rant is this: it was good advice for 26 years. It became slightly less good advice a few months ago. This is a good time to warn overenthuastic people that it’s still good advice in 2026, and to start a discussion about which of its assumptions remain to be true in 2027 and later.

Re: Writing code is cheap now

#484

Post by joe_mamba »

simonw wrote: post #272
joe_mamba wrote: post #199

Earlier quoted context omitted.

>Famously, it took many years for the internet itself to show up in significant productivity gains Yeah but the actual productivity gains that the internet and software tools introduced has had diminishing returns after a while. Like, are people more productive today when they use Outlook and Slack than they were 20 years ago when using IBM Lotus Notes and IBM Sametime? I'm not. Are people more productive with the Ex…

I think the biggest productivity improvements in software development over the last ~20 years came from open source (NPM install X / pip install Y save so much time constantly reinventing wheels) and automated tests.

True, FOSS changed the game at lot, at least in web development.

Re: Writing code is cheap now

#485

Post by nananana9 »

Retr0id wrote: post #312
heisenbit wrote: post #286

Earlier quoted context omitted.

There is demand for non scalable, not committed to be maintained code where smaller issues can tolerated. This demand is currently underserved as coding is somewhat expensive and focused on critical functions.

What are some examples of when buggy code can be tolerated?

Leaf code. Anything that you won't have to build upon long-term and is not super mission critical. Data visualizers, dashboards, internal tools.

Pretty much everywhere where a 80% working tool is better than no tool, and without AI the opportunity cost to write the tool would be too high.

Re: Writing code is cheap now

#486

Post by coldtea »

simonw wrote: post #268
slopinthebag wrote: post #176

Earlier quoted context omitted.

When you talk about maintaining code, do you mean having the LLM do it and you maintain a write-only codebase? Because if you're reading the code yourself and you have a bloated tangled codebase it would make things much harder right? Is the goal basically a codebase where your interactions are mediated through an LLM?

The goal is "good code" based on my list of criteria, which includes both "simple and minimal" and "the design affords future changes". A bloated table codebase isn't good code, because it's harder to understand and makers changes to than the equivalent non-bloated codebase. But... bloat does look a little bit different when you no longer need to optimize code for saving humans typing time. Much of the confusing code…

"Good coding agents" is the new "sufficiently smart compilers"

Re: Writing code is cheap now

#487

Post by eesmith »

simonw wrote: post #330
eesmith wrote: post #289

Earlier quoted context omitted.

My points though are 1) the development isn't actually using red/green TDD, and 2) the result doesn't show "really good results", including not following a very well-defined specification so doesn't work as a concrete example of your description of what the second chapter is supposed to be about. Perhaps you could show the process of refining it more, so it actually is spec compliant and tests all the implemented fea…

Yeah I'm going to ditch those examples and find better ones. I was hoping to illustrate the idea as simply as possible but they're not up to scratch.

Will you be updating the text at https://simonwillison.net/guides/agentic-engineering-pattern...?

As it currently says:

> A significant risk with coding agents is that they might write code that doesn't work, or build code that is unnecessary and never gets used, or both.

> Test-first development helps protect against both of these common mistakes, and also ensures a robust automated test suite that protects against future regressions.

while the ChatGPT generated code contains bugs, contains unnecessary code which never gets used, and the ChatGPT generated test suite is not robust.

(As an example of unnecessary code which never gets used, _FENCE_RE contains "(?P.*)$" but neither the group name nor the group are used, and the pattern is unneeded -- and all of the tests pass without it.)

Your writings are widely read and influential. I think it's important that you let readers know the results produced in your experiment are not actually a complete example of a "fantastic fit" of Red/Green TDD for coding agents, and to highlight their limitations.

Re: Writing code is cheap now

#488

Post by gombosg »

chr15m wrote: post #298
foepys wrote: post #245

Earlier quoted context omitted.

A study last year concluded that while AI coding feels faster it actually isn't. At least in mid 2025. https://news.ycombinator.com/item?id=44522772

That's a good point. Myself is the easiest person to fool. I knocked together a quick analysis of my commit graphs going back several years, if you're interested: https://mccormick.cx/gh/ My average leading up to 2023 was around 2k commits per year. 2023 I started using ChatGPT and I hit my highest commits so far that year at 2,600. 2024 I moved to a different country, which broke my productivity. I started using aid…

Love your approach and that you actually have "before vs. after" numbers to back it up!

I personally also use AI in a similar way, strongly guiding it instead of vibe-coding. It reduces frustration because it surely "types" faster and better than me, including figuring out some syntax nuances.

But often I jump in and do some parts by myself. Either "starting" something (creating a directory, file, method etc.) to let the LLM fill in the "boring" parts, or "finishing" something by me filling in the "important" parts (like business logic etc.).

I think it's way easier to retain authorship and codebase understanding this way, and it's more fun as well (for me).

But in the industry right now there is a heavy push for "vibe coding".

Re: Writing code is cheap now

#489

Post by simonw »

eesmith wrote: post #487
simonw wrote: post #330

Earlier quoted context omitted.

Yeah I'm going to ditch those examples and find better ones. I was hoping to illustrate the idea as simply as possible but they're not up to scratch.

Will you be updating the text at https://simonwillison.net/guides/agentic-engineering-pattern... ? As it currently says: > A significant risk with coding agents is that they might write code that doesn't work, or build code that is unnecessary and never gets used, or both. > Test-first development helps protect against both of these common mistakes, and also ensures a robust automated test suite that protects against…

I'll be replacing the examples with ones that better illustrate the technique. I dashed off those off in a hurry using the wrong tools (I used ChatGPT and Claude directly, not the Coding agent harnesses Claude Code and Codex) and that was a mistake.

Re: Writing code is cheap now

#490

Post by DonHopkins »

Factorio is so much about juggling and re-juggling the trade-offs of doing things by hand versus progressively higher and higher level automation, as you research new technologies like conveyor belts, inserters, logistics and constructor robots, blueprints, etc.

Once you get blueprints, and a big enough industrial base, building vast sprawling expanses of factories like VLSI circuits is cheap, then planning reusable, modular, composable, efficient blueprints becomes the real game.

Post reply on HN